Triple

T3986940
Position Surface form Disambiguated ID Type / Status
Subject Defence Academy of the United Kingdom E86894 entity
Predicate abbreviation P43 FINISHED
Object DAUK
DAUK is the acronym commonly used for the Defence Academy of the United Kingdom, the UK’s central institution for higher education and professional development in defence and security.
 E404030 NE FINISHED

How this triple was built (4 steps)

Every LLM step that produced this triple, in pipeline order — named-entity classification, the disambiguation choices (the exact options shown, with the pick highlighted), and the generated description. The batch + timestamp of each is in the Provenance table below.

NER Named-entity recognition gpt-5-mini
Instruction
Given a phrase, classify it is english named entity (e.g., persons, organizations, works of art) in Latin script, or not (e.g., literals, dates, URLs, verbose phrases). For disambiguation, the statement where the phrase occurs as object is also given. Please return a JSON object with `phrase` (string, the phrase being analyzed) and `is_ne` (boolean, indicating whether the phrase is a Named Entity).
Input
Phrase: DAUK | Statement: [Defence Academy of the United Kingdom, abbreviation, DAUK]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07 
Target entity: DAUK
Context triple: [Defence Academy of the United Kingdom, abbreviation, DAUK]
  • A. DAK
    DAK is the abbreviation for the German Afrika Korps, the German expeditionary force that fought in North Africa during World War II under commanders such as Erwin Rommel.
  • B. Dauch
    Dauch is a surname of French origin borne by individuals such as Martin-Dauch.
  • C. DA
    DA is a postcode area in southeast England covering parts of south-east London and northwest Kent, including towns such as Dartford and Sidcup.
  • D. DA
    DA is the official abbreviation for the United States Department of the Army, the federal agency responsible for organizing, training, and equipping the U.S. Army.
  • E. Doud
    Doud is the maiden surname of Mamie Eisenhower, the First Lady of the United States during Dwight D. Eisenhower’s presidency.
  • F. None of above. chosen
  • G. Unsure - the case is ambiguous/there is not enough information to decide.
NEDg Description generation gpt-5.1
Instruction
Generate a one-sentence description of the target entity. 
You are given a context triple in the form (subject, predicate, object), where the object is the target entity. 
# Instructions
Use the triple to infer relevant information about the entity. Describe the entity based on what is most defining, well-known. 
Avoid repeating the information from the triple, unless really essential.
# Response Format
Return only the sentence: "Description: [one-sentence description of the target entity]"
Input
Entity: DAUK
Triple: [Defence Academy of the United Kingdom, abbreviation, DAUK]
Generated description
DAUK is the acronym commonly used for the Defence Academy of the United Kingdom, the UK’s central institution for higher education and professional development in defence and security.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07 
Target entity: DAUK
Target entity description: DAUK is the acronym commonly used for the Defence Academy of the United Kingdom, the UK’s central institution for higher education and professional development in defence and security.
  • A. DAK
    DAK is the abbreviation for the German Afrika Korps, the German expeditionary force that fought in North Africa during World War II under commanders such as Erwin Rommel.
  • B. Dauch
    Dauch is a surname of French origin borne by individuals such as Martin-Dauch.
  • C. DA
    DA is a postcode area in southeast England covering parts of south-east London and northwest Kent, including towns such as Dartford and Sidcup.
  • D. DA
    DA is the official abbreviation for the United States Department of the Army, the federal agency responsible for organizing, training, and equipping the U.S. Army.
  • E. Doud
    Doud is the maiden surname of Mamie Eisenhower, the First Lady of the United States during Dwight D. Eisenhower’s presidency.
  • F. None of above. chosen

Provenance (5 batches)

The batch behind each pipeline step, in order, with when it ran. Timestamps are batch-level — stages were processed in waves, so the object chain (NER → NED1 → NEDg → NED2) reads in order, but predicate / elicitation batches can sit in a different wave.

Step Stage Batch ID Status When
creating Elicitation batch_69aed93fd9d4819085d3b2137d2346cb completed March 9, 2026, 2:29 p.m.
NER Named-entity recognition batch_69aef9fe355081909b04662ab44fe2ca completed March 9, 2026, 4:49 p.m.
NED1 Entity disambiguation (via context triple) batch_69b5402f72e8819097ce951aac465dc8 completed March 14, 2026, 11:02 a.m.
NEDg Description generation batch_69b54111e5188190ab8ec23124c22981 completed March 14, 2026, 11:05 a.m.
NED2 Entity disambiguation (via description) batch_69b54195261c8190a155b3c0469b0a35 completed March 14, 2026, 11:08 a.m.
Created at: March 9, 2026, 3:33 p.m.